Nicholas H. Barbara

Nicholas H. Barbara, Ruigang Wang, Ian R. Manchester

This paper presents a policy parameterization for learning-based control on nonlinear, partially-observed dynamical systems. The parameterization is based on a nonlinear version of the Youla parameterization and the recently proposed Recurrent Equilibrium Network (REN) class of models. We prove that the resulting Youla-REN parameterization automatically satisfies stability (contraction) and user-tunable robustness (Lipschitz) conditions on the closed-loop system. This means it can be used for safe learning-based control with no additional constraints or projections required to enforce stability or robustness. We test the new policy class in simulation on two reinforcement learning tasks: 1) magnetic suspension, and 2) inverting a rotary-arm pendulum. We find that the Youla-REN performs similarly to existing learning-based and optimal control methods while also ensuring stability and exhibiting improved robustness to adversarial disturbances.

Nicholas H. Barbara, Max Revay, Ruigang Wang et al.

Neural networks are typically sensitive to small input perturbations, leading to unexpected or brittle behaviour. We present RobustNeuralNetworks.jl: a Julia package for neural network models that are constructed to naturally satisfy a set of user-defined robustness metrics. The package is based on the recently proposed Recurrent Equilibrium Network (REN) and Lipschitz-Bounded Deep Network (LBDN) model classes, and is designed to interface directly with Julia's most widely-used machine learning package, Flux.jl. We discuss the theory behind our model parameterization, give an overview of the package, and provide a tutorial demonstrating its use in image classification, reinforcement learning, and nonlinear state-observer design.

Nicholas H. Barbara, Ruigang Wang, Ian R. Manchester

This paper presents a study of robust policy networks in deep reinforcement learning. We investigate the benefits of policy parameterizations that naturally satisfy constraints on their Lipschitz bound, analyzing their empirical performance and robustness on two representative problems: pendulum swing-up and Atari Pong. We illustrate that policy networks with smaller Lipschitz bounds are more robust to disturbances, random noise, and targeted adversarial attacks than unconstrained policies composed of vanilla multi-layer perceptrons or convolutional neural networks. However, the structure of the Lipschitz layer is important. We find that the widely-used method of spectral normalization is too conservative and severely impacts clean performance, whereas more expressive Lipschitz layers such as the recently-proposed Sandwich layer can achieve improved robustness without sacrificing clean performance.

Nicholas H. Barbara, Ruigang Wang, Ian R. Manchester

This paper presents the Robust Recurrent Deep Network (R2DN), a scalable parameterization of robust recurrent neural networks for machine learning and data-driven control. We construct R2DNs as a feedback interconnection of a linear time-invariant system and a 1-Lipschitz deep feedforward network, and directly parameterize the weights so that our models are stable (contracting) and robust to small input perturbations (Lipschitz) by design. Our parameterization uses a structure similar to the previously-proposed recurrent equilibrium networks (RENs), but without the requirement to iteratively solve an equilibrium layer at each time-step. This speeds up model evaluation and backpropagation on GPUs, and makes it computationally feasible to scale up the network size, batch size, and input sequence length in comparison to RENs. We compare R2DNs to RENs on three representative problems in nonlinear system identification, observer design, and learning-based feedback control and find that training and inference are both up to an order of magnitude faster with similar test set performance, and that training/inference times scale more favorably with respect to model expressivity.

Nicholas H. Barbara, Ruigang Wang, Alexandre Megretski et al.

We study parameterizations of stabilizing nonlinear policies for learning-based control. We propose a structure based on a nonlinear version of the Youla-Kucera parameterization combined with robust neural networks such as the recurrent equilibrium network (REN). The resulting parameterizations are unconstrained, and hence can be searched over with first-order optimization methods, while always ensuring closed-loop stability by construction. We study the combination of (a) nonlinear dynamics, (b) partial observation, and (c) incremental closed-loop stability requirements (contraction and Lipschitzness). We find that with any two of these three difficulties, a contracting and Lipschitz Youla parameter always leads to contracting and Lipschitz closed loops. However, if all three hold, then incremental stability can be lost with exogenous disturbances. Instead, a weaker condition is maintained, which we call d-tube contraction and Lipschitzness. We further obtain converse results showing that the proposed parameterization covers all contracting and Lipschitz closed loops for certain classes of nonlinear systems. Numerical experiments illustrate the utility of our parameterization when learning controllers with built-in stability certificates for: (i) "economic" rewards without stabilizing effects; (ii) short training horizons; and (iii) uncertain systems.

Ruigang Wang, Nicholas H. Barbara, Max Revay et al.

This paper proposes a nonlinear policy architecture for control of partially-observed linear dynamical systems providing built-in closed-loop stability guarantees. The policy is based on a nonlinear version of the Youla parameterization, and augments a known stabilizing linear controller with a nonlinear operator from a recently developed class of dynamic neural network models called the recurrent equilibrium network (REN). We prove that RENs are universal approximators of contracting and Lipschitz nonlinear systems, and subsequently show that the the proposed Youla-REN architecture is a universal approximator of stabilizing nonlinear controllers. The REN architecture simplifies learning since unconstrained optimization can be applied, and we consider both a model-based case where exact gradients are available and reinforcement learning using random search with zeroth-order oracles. In simulation examples our method converges faster to better controllers and is more scalable than existing methods, while guaranteeing stability during learning transients.